Umang Gupta

About Me

I am a Ph.D. student at the University of Southern California, advised by Prof. Greg Ver Steeg. I am interested in unsupervised learning, representation learning, and using machine learning for scientific advancement. More recently, I have been working on fairness (1, 2, 3) and privacy (4, 5) problems in machine learning and federated learning (6).

Before that, I worked on finding optimal strategies for Stackelberg security games with deep reinforcement learning and solving catastrophic forgetting in neural networks. Before coming to USC, I spent two years at Visa Inc., Bangalore, employed as a senior software developer, and five wonderful years at IIT Delhi, concluding with a Dual Degree (B.Tech and M.Tech) in Electrical Engineering.

Research Interests

• Machine Learning: Fairness, Privacy, Federated & Distributed Training
• Applications: Natural Language Processing, Neuroimaging

Selected Publications

• Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversal
  Umang Gupta

  , Jwala Dhamala, Varun Kumar, Apurv Verma, Yada Pruksachatkun, Satyapriya Krishna, Rahul Gupta, Kai-Wei Chang, Greg Ver Steeg, Aram Galstyan

  Findings of the Association for Computational Linguistics (ACL 2022)

  We mitigate gender disparity in text generation while performing knowledge distillation by exploiting counterfactual role-reversed texts for training.

• Membership Inference Attacks on Deep Regression Models for Neuroimaging
  Umang Gupta

  , Dimitris Stripelis, Pradeep K. Lam, Paul Thompson, Jose Luis Ambite, Greg Ver Steeg

  Medical Imaging and Deep Learning (2021)

  We illustrate that allowing access to model parameters can leak private information about the training set. We observed strong correlations between privacy leakage and overfitting, indicating that reducing overfitting may ensure privacy.

• Controllable Guarantees for Fair Outcomes via Contrastive Information Estimation
  Umang Gupta

  , Aaron Ferber, Bistra Dilkina, Greg Ver Steeg

  The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21)

  We show that limiting the mutual information between the representations limits any classifier's statistical parity. To this end, we propose a novel method for controlling fairness through mutual information based on contrastive information estimators.

  • video
  • code
• Improved Brain Age Estimation with Slice-based Set Networks
  Umang Gupta

  , Pradeep K. Lam, Greg Ver Steeg, Paul M. Thompson

  18th International Symposium on Biomedical Imaging (ISBI-21)

  We propose a new architecture for making predictions over 3D-MRIs prediction, which works by encoding a single 2D slice in an MRI with a deep 2D-CNN model and integrating the information from these 2D-slice encodings with permutation invariant layers.

  • code
  • follow-up work with transfer learning @ ISBI'23
• DeepFP for Finding Nash Equilibrium in Continuous Action Spaces
  Nitin Kamra,

  Umang Gupta

  , Kai Wang, Fei Fang, Yan Liu, Milind Tambe

  Decision and Game Theory for Security (GameSec 2019)

  We propose an approximate extension of fictitious play in continuous action spaces by modeling best responses with implicit density models.

  • Also appeared as extended abstract at AAMAS 2019
• Deep Generative Dual Memory Network for Continual Learning
  Nitin Kamra,

  Umang Gupta

  , Yan Liu

  arXiv:1710.10368

  Deriving inspiration from human complementary learning systems (hippocampus and neocortex), we develop a dual generative memory architecture that consolidates memory via generative replay and is capable of learning continuously from sequentially incoming tasks while averting catastrophic forgetting.

Not Research

• I enjoy hacking together JS and html to create useful pages. I once parsed conference proceddings to enable searching through them.
• Basic chrome add-ons to hide youtube recommendations and enhance Grammarly editor.
• You can often find me answering PyTorch questions on StackOverflow.

Powered by Jekyll and Minimal Light theme.